INDEX
Explanations
information related to awards, reviews, and critical reception of a video game or a similar media production
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
792
+0.11
0.3%
453
+0.10
0.3%
89
+0.08
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1782
+0.11
0.03
1951
+0.10
0.03
792
+0.08
0.02
Negative Logits
Mlle
-1.17
ftu
-1.16
tranf
-1.10
tupperware
-1.10
fup
-1.08
fta
-1.05
impra
-1.05
ftre
-1.03
oleo
-1.03
embodi
-1.03
POSITIVE LOGITS
Metacritic
0.72
rating
0.61
reviews
0.59
ratings
0.58
critics
0.54
score
0.53
Reviews
0.53
score
0.53
<bos>
0.53
reviews
0.53
Activations Density 0.126%